Perceiving spatiotemporal traffic anomalies from sparse representation-modeled city dynamics
- PDF / 1,670,165 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 18 Downloads / 248 Views
ORIGINAL ARTICLE
Perceiving spatiotemporal traffic anomalies from sparse representation-modeled city dynamics Jun Gao 1 & Daqing Zheng 2,3
&
Su Yang 1
Received: 20 February 2020 / Accepted: 10 October 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Early perception of anomaly traffic patterns, both spatially and temporally, is of importance for emergency response in the smart cities. To capture the spatiotemporal correlations among traffic flows for city dynamics modeling in correspondence with normal states, we conduct sparse representation on taxi activity over spatially partitioned cells in a city. We can perceive the deviation from the normal evolution of traffic flows and find the traffic anomalies. This method roots in the ideal of global traffic flow network detection. Therefore, it is more informative than local statistics since traffic flows evolve in a mutually interacting manner to spread out all over the city. The experimental results confirm its predictive power in detecting spatiotemporal traffic anomalies. Keywords Traffic dynamics . Anomaly detection . Traffic anomaly . Sparse representation
1 Introduction Perceiving and locating traffic anomalies are a crucial issue for emergency response in smart cities since they can act as early signals to indicate abnormal events to appear or being selforganized [35]. Here, traffic anomalies refer to the strange behavior patterns of a transportation system that deviate from its historical performance. One of the most famous events closely related to traffic anomaly detection is the Shanghai Bund trampling incident that occurred on the evening of The three authors contributed equally to this work. * Daqing Zheng [email protected] * Su Yang [email protected] Jun Gao [email protected] 1
Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai 200433, China
2
School of Information Management & Information Systems, Shanghai University of Finance & Economics, Shanghai 200433, China
3
Shanghai Key Laboratory of Financial Information Technology, Shanghai University of Finance & Economics, Shanghai, China
December 31, 2014. If we can discover this anomaly and intervene in advance, we can avoid this disaster. The challenge to identify anomalies lies in that traffic flows interact mutually throughout the whole road network, and the behaviors of the transportation system are complex and varying continuously, which incurs the difficulty in identifying what kind of traffic patterns correspond with natural evolution and what are abnormal signals. Furthermore, locating the place where anomalies appear or will appear shortly makes the problem even more challenging. Due to the diverse patterns of abnormalities in a transportation system, the goal of this study is not to capture such irregularities in the sense of statistics, as we believe that such outlying patterns may not be distinguishable in a statistical significance. On the contrary, we aim to reveal the traffic patter
Data Loading...
